© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213110
    Prev
    Next
    INDEX
    Explanations

    various languages and contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    indeterminate form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wzglę
    0.43
    isht
    0.43
     Lust
    0.42
    las
    0.42
    ală
    0.42
    赖
    0.41
     ответы
    0.41
     часть
    0.40
    ለው
    0.40
    ość
    0.40
    POSITIVE LOGITS
     Puedes
    0.48
     عندما
    0.47
     TEMPERATURE
    0.45
     beim
    0.43
     irão
    0.43
     Beim
    0.43
    絢
    0.42
     especializados
    0.42
     একেবারেই
    0.42
     segura
    0.42
    Activations Density 0.000%

    No Known Activations